Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15263
    Prev
    Next
    INDEX
    Explanations

    meta

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     information
    -0.28
     hearing
    -0.28
    çļĦä¿¡æģ¯
    -0.27
    ums
    -0.27
     info
    -0.26
     dry
    -0.26
    frag
    -0.25
    åIJ¬çĿĢ
    -0.25
    PostalCodes
    -0.25
     INFORMATION
    -0.25
    POSITIVE LOGITS
    ampo
    0.30
    section
    0.29
     section
    0.28
    èħIJ
    0.26
    last
    0.26
    ãĤ¨ãĥªãĤ¢
    0.26
    erea
    0.26
    enan
    0.26
     Section
    0.25
    æļ´åĬĽ
    0.25
    Activations Density 0.105%

    No Known Activations